ProtT3_model / data_provider /gal_helpers.py
yuccaaa's picture
Add files using upload-large-folder tool
4d12519 verified
import re
# we split individual characters inside special tokens like [START_DNA]
CUSTOM_SEQ_RE = re.compile(r"(\[START_(DNA|SMILES|I_SMILES|AMINO)])(.*?)(\[END_\2])")
# token added to implement a custom sequence tokenization. This token is added at
# corpus cleaning step and removed in pretokenization. The digits are added to increase the chance
# that they do not occur in the corpus. The digits are escaped so that the token does not appear
# literally in the source code in case we ever include it in the training data.
SPLIT_MARKER = f"SPL{1}T-TH{1}S-Pl3A5E"
def _insert_split_marker(m: re.Match):
"""
Applies split marker based on a regex match of special tokens such as
[START_DNA].
Parameters
----------
n : str
Input text to split
Returns
----------
str - the text with the split token added
"""
start_token, _, sequence, end_token = m.groups()
sequence = re.sub(r"(.)", fr"{SPLIT_MARKER}\1", sequence, flags=re.DOTALL)
return f"{start_token}{sequence}{SPLIT_MARKER}{end_token}"
def escape_custom_split_sequence(text):
"""
Applies custom splitting to the text for GALILEO's tokenization
Parameters
----------
text : str
Input text to split
Returns
----------
str - the text with the split token added
"""
return CUSTOM_SEQ_RE.sub(_insert_split_marker, text)